Gurkengewuerz/ImgScroll
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Fixed 8muses ripper

Browse Source
This commit is contained in:
cyian-1756 2017-06-25 11:58:37 -04:00
parent 55657dc0bf
commit 7610ae89a7
1 changed files with 44 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

65
src/main/java/com/rarchives/ripme/ripper/rippers/EightmusesRipper.java
View File

@ -77,32 +77,55 @@ public class EightmusesRipper extends AbstractHTMLRipper {
@Override @Override
public List<String> getURLsFromPage(Document page) { public List<String> getURLsFromPage(Document page) {
List<String> imageURLs = new ArrayList<String>(); List<String> imageURLs = new ArrayList<String>();
if (page.select(".preview > span").size() > 0) { // get the first image link on the page and check if the last char in it is a number
// if it is a number then we're ripping a comic if not it's a subalbum
String firstImageLink = page.select(".page-gallery > div > div > div.gallery > a.t-hover").first().attr("href");
Pattern p = Pattern.compile("/comix/[a-zA-Z0-9\\-_/]*/\\d+");
Matcher m = p.matcher(firstImageLink);
if (!m.matches()) {
logger.info("Ripping subalbums");
// Page contains subalbums (not images) // Page contains subalbums (not images)
Elements albumElements = page.select("a.preview"); Elements albumElements = page.select(".page-gallery > div > div > div.gallery > a.t-hover");
List<Element> albumsList = albumElements.subList(0, albumElements.size()); List<Element> albumsList = albumElements.subList(0, albumElements.size());
Collections.reverse(albumsList); Collections.reverse(albumsList);
// Iterate over elements in reverse order // Iterate over elements in reverse order
for (Element subalbum : albumsList) { for (Element subalbum : albumsList) {
String subUrl = subalbum.attr("href"); String subUrl = subalbum.attr("href");
subUrl = subUrl.replaceAll("\\.\\./", ""); // This if is to skip ads which don't have a href
if (subUrl.startsWith("//")) { if (subUrl != "") {
subUrl = "http:"; subUrl = subUrl.replaceAll("\\.\\./", "");
} if (subUrl.startsWith("//")) {
else if (!subUrl.startsWith("http://")) { subUrl = "http:";
subUrl = "http://www.8muses.com/" + subUrl; }
} else if (!subUrl.startsWith("http://")) {
try { subUrl = "http://www.8muses.com" + subUrl;
logger.info("Retrieving " + subUrl); }
sendUpdate(STATUS.LOADING_RESOURCE, subUrl); try {
Document subPage = Http.url(subUrl).get(); logger.info("Retrieving " + subUrl);
// Get all images in subalbum, add to list. sendUpdate(STATUS.LOADING_RESOURCE, subUrl);
List<String> subalbumImages = getURLsFromPage(subPage); Document subPage = Http.url(subUrl).get();
logger.info("Found " + subalbumImages.size() + " images in subalbum"); // Get all images in subalbum, add to list.
imageURLs.addAll(subalbumImages); List<String> subalbumImages = getURLsFromPage(subPage);
} catch (IOException e) { String albumTitle = subPage.select("title").first().text();
logger.warn("Error while loading subalbum " + subUrl, e); albumTitle = albumTitle.replace("Sex and Porn Comics", "");
continue; albumTitle = albumTitle.replace("|", "");
albumTitle = albumTitle.replace("8muses", "");
albumTitle = albumTitle.replaceAll("-", "_");
albumTitle = albumTitle.replaceAll(" ", "_");
albumTitle = albumTitle.replaceAll("___", "_");
albumTitle = albumTitle.replaceAll("__", "_");
logger.info("Found " + subalbumImages.size() + " images in subalbum");
imageURLs.addAll(subalbumImages);
int x = 1;
for (String image : subalbumImages) {
URL image_url = new URL(image);
addURLToDownload(image_url, Integer.toString(x) + "_", albumTitle, this.url.toExternalForm(), cookies);
x = x + 1;
}
} catch (IOException e) {
logger.warn("Error while loading subalbum " + subUrl, e);
continue;
}
} }
} }
} }
@ -144,7 +167,7 @@ public class EightmusesRipper extends AbstractHTMLRipper {
sendUpdate(STATUS.LOADING_RESOURCE, imageUrl); sendUpdate(STATUS.LOADING_RESOURCE, imageUrl);
Document doc = new Http(imageUrl).get(); // Retrieve the webpage of the image URL Document doc = new Http(imageUrl).get(); // Retrieve the webpage of the image URL
Element fullSizeImage = doc.select(".photo").first(); // Select the "photo" element from the page (there should only be 1) Element fullSizeImage = doc.select(".photo").first(); // Select the "photo" element from the page (there should only be 1)
String path = "https://cdn.ampproject.org/i/s/www.8muses.com/data/ufu/small/" + fullSizeImage.children().select("#imageName").attr("value"); // Append the path to the fullsize image file to the standard prefix String path = "https://cdn.ampproject.org/i/s/www.8muses.com/data/fu/small/" + fullSizeImage.children().select("#imageName").attr("value"); // Append the path to the fullsize image file to the standard prefix
return path; return path;
} }